{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/end-to-end-learning-of-keypoint","title":"Learning of feature points without additional supervision improves reinforcement learning from images","arxiv_id":"2106.07995","date":"2021-06-15","proceeding":null,"authors":["Rinu Boney","Alexander Ilin","Juho Kannala"],"abstract":"In many control problems that include vision, optimal controls can be inferred from the location of the objects in the scene. This information can be represented using feature points, which is a list of spatial locations in learned feature maps of an input image. Previous works show that feature points learned using unsupervised pre-training or human supervision can provide good features for control tasks. In this paper, we show that it is possible to learn efficient feature point representations end-to-end, without the need for unsupervised pre-training, decoders, or additional losses. Our proposed architecture consists of a differentiable feature point extractor that feeds the coordinates of the estimated feature points directly to a soft actor-critic agent. The proposed algorithm yields performance competitive to the state-of-the art on DeepMind Control Suite tasks.","url_abs":"https://arxiv.org/abs/2106.07995v3","url_pdf":"https://arxiv.org/pdf/2106.07995v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"end-to-end-learning-of-keypoint","repo_url":"https://github.com/rinuboney/fpac","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"end-to-end-learning-of-keypoint","repo_url":"https://github.com/rinuboney/keyq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"unsupervised-pre-training","task_name":"Unsupervised Pre-training"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.07995","atlas_url":"https://app.syntology.ai/?focus=2106.07995","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.07995"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rinuboney/keyq","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rinuboney/fpac","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"979a04c1a1e13358","entry":"compute_heatmaps","repo":"rinuboney/fpac","repo_kind":"official","path":"keypoints_encoder.py","file_url":"https://github.com/rinuboney/fpac/blob/HEAD/keypoints_encoder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"979a04c1a1e13358"}},{"code_sha256_prefix":"6df9e012797c56a6","entry":"compute_keypoints_1d","repo":"rinuboney/fpac","repo_kind":"official","path":"keypoints_encoder.py","file_url":"https://github.com/rinuboney/fpac/blob/HEAD/keypoints_encoder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6df9e012797c56a6"}},{"code_sha256_prefix":"1329feb98629ca3f","entry":"compute_pixel_offsets","repo":"rinuboney/fpac","repo_kind":"official","path":"dm_wrappers.py","file_url":"https://github.com/rinuboney/fpac/blob/HEAD/dm_wrappers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1329feb98629ca3f"}},{"code_sha256_prefix":"3e01094de0235cb4","entry":"xyz2pixels","repo":"rinuboney/fpac","repo_kind":"official","path":"dm_wrappers.py","file_url":"https://github.com/rinuboney/fpac/blob/HEAD/dm_wrappers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3e01094de0235cb4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}